NNAlign statistics

Tool stats & trends

Looking to identify usage trends or leading experts?

NNAlign specifications


Unique identifier OMICS_06758
Name NNAlign
Software type Package/Module
Interface Command line interface
Restrictions to use Academic or non-commercial use
Operating system Unix/Linux
Computer skills Advanced
Stability Stable
Maintained Yes


No version available


  • person_outline Massimo Andreatta


Unique identifier OMICS_06758
Name NNAlign
Interface Web user interface
Restrictions to use None
Input data Some peptides.
Input format PEPTIDE, FASTA
Computer skills Basic
Version 2.0
Stability Stable
Maintained Yes


  • person_outline Massimo Andreatta

Publications for NNAlign

NNAlign citations


Time Frequency Analysis of Peptide Microarray Data: Application to Brain Cancer Immunosignatures

Cancer Inform
PMCID: 4476374
PMID: 26157331
DOI: 10.4137/CIn.s17285

[…] integrate peptide sequences and mean fluorescence intensity (MFI) measurements to identify epitope sequences. Although mimotopes can be abundant, they do not help in tracking of an eliciting antigen. NNAlign is an algorithm that attempts to solve this problem by generating neural network models from subsets of the peptide array data and then combining those multiple models into a single motif. Thi […]


Mapping the Pareto Optimal Design Space for a Functionally Deimmunized Biotherapeutic Candidate

PLoS Comput Biol
PMCID: 4288714
PMID: 25568954
DOI: 10.1371/journal.pcbi.1003988

[…] lele 0701 (59%). Overall, we observed a 13% false positive rate and a 22% false negative rate, similar to those we have reported previously , . Comparable analyses using the newer IEDB consensus and NNAlign prediction methods revealed that, in this instance, no single predictor exhibited dominant accuracy across all four alleles (, and ). In particular, the ProPred predictor was comparable to t […]


Different binding motifs of the celiac disease associated HLA molecules DQ2.5, DQ2.2, and DQ7.5 revealed by relative quantitative proteomics of endogenous peptide repertoires

PMCID: 4297300
PMID: 25502872
DOI: 10.1007/s00251-014-0819-9

[…] o assess the binding specificity of the DQ2.5, DQ2.2, and DQ7.5 molecules, we subjected the quantitative values for eluted peptides as listed in Supplemental Table  to the neural network-based method NNAlign (Andreatta et al. ). The peptide-binding motifs obtained were compared with peptide-binding motifs predicted by the NetMHCIIpan-3.0 (Karosiene et al. ) that was trained on an extensive set of […]


MHC2MIL: a novel multiple instance learning based method for MHC II peptide binding prediction by considering peptide flanking region and residue positions

BMC Genomics
PMCID: 4290625
PMID: 25521198
DOI: 10.1186/1471-2164-15-S9-S9

[…] cess. More experimental studies should be carried out to elucidate the role of these two positions.Our experimental results suggest that, for the MHC-II pepitde binding prediction, MHC2MIL, MH2SK and NNalign are the three best predicting methods. Differing from NN-align using multiple neural network ensembles, both MHC2SK and MHC2MIL use a single classifier. Moreover, the underlying principles of […]


Looking to check out a full list of citations?

NNAlign institution(s)
Instituto de Investigaciones Biotecnologicas, Universidad Nacional de San Martin, San Martin, Argentina; Department of Bio and Health Informatics, Technical University of Denmark, Lyngby, Denmark
NNAlign funding source(s)
Supported by National Institutes of Health [HHSN272201200010C]; Agencia Nacional de Promocion Cientifica y Tecnologica, Argentina [PICT-2012-0115]; Department for International Development of the United Kingdom and the Bill and Melinda Gates Foundation [OPP1078791].

NNAlign reviews

star_border star_border star_border star_border star_border
star star star star star

Be the first to review NNAlign